75 results
Dual-pipeline compaction for DeepSeek Harness: official server-side Responses compaction v2 for OpenAI-routed targets, with a deterministic VCC-style local compiler (zero model calls) as the default fallback and for every other provider.
DeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.
Whole-disk ctx.fileReferences provider for DeepSeek Harness: Everything-backed instant search with a bounded cross-platform fallback index, fuzzy matching, and regex queries
Notify me when DSH needs me: desktop notification (with tab-title fallback) when an approval prompt or an ask-user-question card appears while the page is in the background.
DSH web GUI plugin: Cursor-style Git commit-chain (链路图) panel — SVG lane topology, commit detail/diff, guarded branch switching. Dual-face Cordis plugin (host git service + browser React panel); mounts as a dsh-better-sidebar tab with a floating-panel fallback.
DeepSeek Harness plugin: pick configured model providers, and when a model fails with a model-related error the request automatically falls through the provider group's models (then the next selected provider) until one works, so the unfinished task keeps going. Adds its own Settings tab.
DeepSeek Harness (dsh) plugin: route one request to a modality-capable fallback model instead of forcing the whole session onto a single model.
DSH host bundle plugin: builds a two-level (category + skill) recall index over all local SKILL.md files and routes a natural-language intent to the best-matching skills, with three-state (hit / low-confidence / miss) fallback.
Bounded fallback recovery for DSH rate limits, empty responses, and truncated model output
Show code changes in the dsh web GUI conversation: inline line-level diff inside edit/write tool cards with a streaming reveal animation, plus a per-turn file-change summary card (git-first, argument-diff fallback).
Multi-platform IM gateway for DeepSeek Harness (fork of dsh-im-hub with media): Telegram voice/photo/document/video + reply handling, STT (Deepgram primary, HF Whisper fallback), outbound MEDIA: markers. Feishu/WeCom kept as-is.
DeepSeek Harness plugin: content-routing LLM adapter. Text-only requests go to DeepSeek; requests containing images go to a user-configurable OpenAI-compatible vision provider. Read_image works natively for text-only models.
Multi-level provider fallback for same-named models in the DeepSeek Harness
Session topic titles for DeepSeek Harness: LLM-generated titles for sessions stuck on the prompt-excerpt fallback, retry on every turn end, plus a /topics-size endpoint for the hover-card size patch (out-of-tree plugin)
Native multi-provider web search for the DeepSeek Harness: Tavily, Exa, Firecrawl, Brave Search, and Serper as keyed providers with an automatic keyless DuckDuckGo fallback, plugged into the harness ctx.web seam so the built-in web_search tool works even without a DeepSeek API key.
DSH profile plugin: converts read_image PNG/WebP attachments to opaque sRGB JPEG so LM Studio's openai-completions endpoint accepts them
Plugin Cordis para o DeepSeek Harness v0.1: interceta a camada HTTP (auth barrier sobre o fallback da Web UI) e orquestra subprocessos de longa duracao com ciclo de vida reversivel.
Image auto-describe provider for the DeepSeek Harness apiproxy admission seam: transcribes pasted images through configurable vision routes (Qwen first, GLM fallback) so text-only session models still receive image prompts.
Lightweight DSH upload bridge: images and common documents become workspace paths so a text-only DeepSeek model can read them with Qwen-MM-Plugins vision tools.
MCP orchestration layer for DeepSeek Harness — multi-server routing, health monitoring, fallback, and tool aggregation
Persistent DeepSeek Harness scenario router with settings-driven model dropdowns, fallback routing, and Web UI settings.
Task Runner 任务拆解模式：主代理把大任务拆成独立子任务、派给子代理（默认本地模型）并行执行再综合结果；并发数与 worker/fallback/orchestrator 模型可在设置面板图形化配置。安装时自动把 agent preset 装进 ~/.dsh/.agent-presets/。
Fallback network proxy for DeepSeek Harness: detects system proxies, probes overseas connectivity (Google/GitHub), routes dsh outbound HTTP through a working local proxy when direct access fails.
Kimi Coding web search and fetch providers for the DeepSeek Harness — one coding-plan key fills both ctx.web seams, with a dedicated settings GUI card and credential fallbacks down to the Kimi CLI config file